JavaScript Web API for Text-to-Speech and Speech-to-Text.

Maintained fork of country-language with zero-dependencies. Query languages spoken to a country or countries where people speak a language.

Query languages spoken to a country or countries where people speak a language.

List of 74,286 words sorted by frequency of use in spoken English

MCP server for Spoken — fetch podcast transcripts as clean Markdown with real speaker names. Built for AI agents.

Give Claude Code a voice — selective, tasteful spoken summaries and attention cues. Quiet by default.

Isomorphic rules engine based on spoken language verb tenses.

Voice assistant orchestrator for Signal K — voice commands in, spoken announcements out.

Shared distress plumbing (event store, chart markers, spoken/logbook rendering, notifications) for SignalK distress plugins.

a11y-now plugin: big caption bar mirroring spoken text

Bat spoken language identification engine for web browsers (via WebAssembly)

Artifical Spoken Language - Kernel (人造語核心)

TOTP but you say it out loud. Derive time-rotating, human-speakable verification tokens from a shared secret.

Helps you to collect feedback and leads using the most spoken language in the world: the emoji.

Official MCP server that lets AI agents push spoken announcements into Announcr via signed webhooks

Runs voice conversations with live transcription, chat orchestration, and spoken replies.

Your agent's output as audio — spoken narration, monologue, two-host podcast, or reactive music. For Claude Code, Codex, Gemini, and other agentic CLIs. Local-first.

Servanda in-situ gestures: the confirm card, reaction-confirm, and thin platform shims for the surfaces where promises are actually spoken

Bidirectional voice for a composer — open mic, live transcript, spoken replies, barge-in. One machine and one button, shared by hanzo.chat and hanzo.app.

 Add text-to-speech (TTS) to content, with playback controls, read-along highlighting, multi-lingual support, and settings for rate, pitch, and voice.